On Apr 17, 5:46 pm, Bill Ward wrote:
On Thu, 17 Apr 2008 04:05:28 -0700, John M. wrote:
On Apr 17, 1:53 am, Bill Ward wrote:
On Wed, 16 Apr 2008 14:19:15 -0700, John M. wrote:
On Apr 16, 10:00 pm, Bill Ward wrote:
On Wed, 16 Apr 2008 10:54:34 -0700, John M. wrote:
On Apr 16, 5:51 pm, Bill Ward
wrote:
On Tue, 15 Apr 2008 23:37:39 -0700, John M. wrote:
On Apr 15, 8:42 am, Bill Ward
wrote:
On Mon, 14 Apr 2008 14:12:43 -0700, John M. wrote:
On Apr 13, 10:53 am, Bill Ward
wrote:
On Sat, 12 Apr 2008 00:32:46 -0700, John M. wrote:
On Apr 12, 1:49 am, Bill Ward
wrote:
On Fri, 11 Apr 2008 12:55:40 -0700, John M. wrote:
On Apr 11, 9:15 pm, Bill Ward
wrote:
On Thu, 10 Apr 2008 11:14:20 -0700, John M. wrote:
On Apr 10, 1:43 pm, "Paul E. Lehmann"
wrote:
Bill Ward wrote:
On Wed, 09 Apr 2008 13:12:25 -0700, Roger Coppock
wrote:

On Apr 9, 8:34 am, Bill Ward
wrote:
On Wed, 09 Apr 2008 07:04:24 -0700, matt_sykes
wrote:
On 9 Apr, 10:24, Roger Coppock
wrote:
On Apr 8, 8:01 pm, Poetic Justice
-n-

Dog.com wrote:
Roger Coppock wrote:
March ties for 3rd warmest on NASA's
129-year record.

Why is NASA the official keeper of the
temperature?

NASA Goddard Institute for Space Studies
offers data, as do several other
organizations. I use NASA's data because
GISS corrects for UHI using nighttime earth
shine, artificial lighting, measured from
satellites. IMHO, this method is better than
using census data to locate urban areas.

That is a feeble way to adjust for UHI.

The ONLY way to adjust for UHI is to put a
station in a rural area near to the urban
station to act as a control (being a
sicnetist you wold know this of course).

Mind you, one you have done that you might as
well ignore the urban station data since
rural data is true surface temp.

And what happens when you do that? You get
no warming trend. RURAL STATIONS ACROSS THE
GLOBE SHOW NO OVERALL TEMPERATURE TREND.

Roger can't comprehend that bad data is worse
than no data. Unless you're trying to scare
people, of course.

If you have better data, or a method for UHI
correction, you are more than
welcome to present them here. Until then the
data presented above are a better indication of
reality than your fantasies.

Fantasies aren't science, whether they're mine or
NASA's. That's the problem with trying to
"correct" bad data. If it's bad, it can't be
used - it's a fantasy based on invalid
assumptions. Averaging bad data with with good
data hides the problem, but doesn't fix it.

It is even worse than that. I suspect there is an
analogy with wine making. I knew of a winemaker
who had a small amount of wine made from under ripe
grapes. He blended it (10%) with some good wine
90%).
That small amount ruined the whole lot. A "Little
BAD
Goes a LONG ways". I suspect the same is true of
data. A little bad or incorrect can have effects
that are way beyond suspected results.

Such are the musings of a statistical illiterate. In
actual practice, the way to avoid problems from
extraneous or erroneous data (ie. bad) is to swamp
it by using large sample sizes. If you measure the
height of 100 men taken at random, the mean height
will be virtually unchanged should one or two of
them be giants or dwarves.

This is what happens in practice with temperature
data. Very large sample size ensures that the famous
UHIs will have little effect on the calculated
global means.

Only if you can prove the assumption that all errors
are symmetrically distributed. Otherwise it's a
fantasy. Or a hoax.

Ah. Another statistical illiterate crawls from the
woodwork, to give us his take on something he knows
little or nothing about.

The manner in which the residuals are distributed is
immaterial. It is merely required that their
distribution remains the same in repeat samples.

So it doesn't matter to you if there are more errors
showing increasing warming than showing cooling? I think
I see your problem.
You are reading "residuals", where I wrote "errors".
Don't you know
the difference?

Generally speaking, statistical errors can never be
quantified. I simply corrected your sloppy language, as it
was clear to what you referred.

Then you don't understand. An "error" in a measurement is
the difference between the measured value and the "true
value", as measured by a perfect sensor and protocol.

A "residual" is the difference between the observed
measurement and the value calculated by some mathematical
model (least squares line, for Roger).

Which, as I pointed out already, was what you meant when you
wrote error. You really ought to try to comprehend the
subject matter before posting.

Your mind reading capability is just as bad as your statistical
understanding. I wrote "error" because it says exactly what I
meant. If you actually understood measurement error, you'd know
that you can never "average out" a systemic error.

An error applies individually to each measurement,
independent of all the others. The residuals simply tell
how well the measurement fits the model. If errors are
biased high (e.g. air conditioning waste heat increasing
with time), the signal will be biased high, and attempts to
"correct" the error without knowing the exact value will
simply corrupt the data.

I notice you didn't comment on the above. Do you agree, or
just not understand it?
How can anyone comment on word spaghetti. You need to reply
using a language that is comprehensible.

OK, so you didn't understand it. That's what I thought. You need
to, though, if you intend to be taken seriously as an
experimenter.

Is that the best you can offer? As someone who once chided me for
failing to re-re-explain an obvious point to a notorious troll on
this ng, surely you can rephrase your over-our-heads statement to
make it something understandable by us ordinary statistics users.
How about:"A residual (or fitting error) is an observable estimate
of the unobservable statistical error." Oh! No! That's the
erroneous statement falsely put onto a Wikipedia statistics page by
some naughty vandal, and still waiting for you to correct it. When
are you going to get around to it? The world and his mother are
going down the tubes, statistically speaking, because of your
procrastination.

Is the qualifier "fitting" as in "fitting error" over your head also?

Nope. Though I note my sarcasm is over yours, it seems.
No riposte. Are you running out of steam. Or perhaps youd like me to snip
some of the irrelevant material in this sub-thread ;-)
Yes, or no? Or can you not find my post material because of all the
useless and extraneous stuff that I have steadfastly refused to cut,
so as not to give you an excuse for more of your nonsense about
snipping is bad because bandwidth is cheap?
It's referring to a residual as a fitting error because it is the
difference between the model projection and the actual data. IOW how
well the model "fits" the data, as I explained previously. That's
what I find so humorous - your "rebuttal" actually confirmed my
explanation, but you had no clue. There is no need for me to rewrite
the wiki, as it is correct AFAIC.

That wasn't what you implied though, was it? start quote
Wiki? Whoopteedoo. I'm so impressed. Is that the best google hit
you
could find?
end quote

You see implications that aren't there.

Bill the denialist at work, as ever.
Oh go on. Deny it ;-)
I'm glad you now seem to comprehend the meaning of this particular
jargon. Another jargon word above that you seem to be mystified by is
systematic which you refer to as "systemic". These errors are only a
problem in repetetive data gathering if observers make changes to
their protocol or if data sets from different observers are merged. I
recommend you read my paper on the subject in "The Ring" 26(1) pp71 -
78 (2004).

You were wise to shift from chemistry to birds - you wouldn't get far in
experimental science.

Is that a comment made after reading my paper, or instead of? Don't bother
to answer. I'm sure I already know and the question becomes rhetorical.
Wasn't it nice of me to save you that embarrassment.

You need to understand the word "estimate". The measurement is an
estimate of the "true" value - the difference is often called
"measurement error". A model (a straight line or sine curve in
Roger's case) can be invented to estimate what would be measured at
points other than those taken.

Which brings us back to what you wrote. start quote Only if you can
prove the assumption that all errors are
symmetrically distributed. Otherwise it's a fantasy. Or a hoax.
end quote
I hope now you can see that residual or "fitting error" is what you
meant and that when I corrected you by writing residual, I was
actually bailing you out. Glad to be of service.

No, I'm referring specifically to the measurement error, not the fitting
error. Apparently you didn't read the next paragraph. Pay attention.
I read all the paragraphs. The difference between us is that I understand
them while it seems you cannot or will not.

If you mean measurement error you also need to specify which kind of
measurement errors. These can not only be systematic ("systemic" is a
different word by-the-way and is not used in this context by staisticians)
or random (as in white noise) but also due to rounding continuous
variables before compounding into ratios or other derived forms of the
variable. But having read my paper you already know this, right?

You are confusing measurement error with data handling error.

Nope. That's not what I'm talking about. That is yet another form of
error.

Statisticians don't necessarily need to know the difference, but
instrument designers and experimentalists do. Measurement error occurs
between the "true value" and the output of the sensor.

So to return to my point that there are various measurement errors.
The sensor may have been mis-calibrated or have drifted out of
calibration - systematic error occurs. An earth tremor or large lorry
passing by the lab might upset movement sensitive components - a
random error. The sensor might give output to three significant
figures - a possible rounding error between 0.5% and ca. 0.05%. All
three can be classed as measurement errors, yet each needs to be
addressed differently by an investigator trying to get a useable value
for a variable.

You could argue
over whether a microprocessor program is part of the sensor, but after the
value is available to the user, data handling errors take over, such as
trying to "correct" corrupt data, which was my original point.

Your original point is still here in the thread and you should have re-
read it before posting. start quote Only if you can prove the
assumption that all errors are symmetrically distributed. Otherwise
it's a fantasy. Or a hoax.
end quote

No mention of what you meant by "errors", of which one now identifies
four distinct types, three of which class as measurement error
(collectively resulting in 'residuals') and one due to (perhaps inept
or deceitful) data handling. The importance of being precise in choice
of jargon impresses itself on me at this point. I trust it does
likewise to you.

The difference between the actual data and the model estimate is
usually called a "residual", perhaps because it represents the
"residue" the model doesn't account for. The wiki you quoted called
it a "fitting error", which also seems reasonable.

And, yes, that's about the best I can do. After all, I've never
claimed any particular talent in statistics, yet I'm the one that
has to explain it to you.
Err. Actually it was Sokal and Rohlf that explained it to me long ago.
But I hope in response to my prodding you have obtained a slightly
better understanding than previously.

You're funny even when you're pathetic.

Does that mean your understanding is still close to zero. And I fondly
imagined you might just be picking up a few pointers.

No one is faulting your imagination. It's just overworked.

It's kind of funny seeing you accuse others of being
"statistical illiterates", with "sloppy language", when you
clearly don't have a clue what you're talking about. People
notice these things, you know.
Let's hope they get a laugh from your nonsense, at least.
Here's a line from Wikipedia that statisticians have failed
to spot and correct: "A residual (or fitting error), on the
other hand, is an observable estimate of the unobservable
statistical error." Anyone can write in Wikipedia so why
don't you correct this yourself?

Wiki? Whoopteedoo. I'm so impressed. Is that the best google
hit you could find? Your condescenscion isn't really working
for you, you know.
Ah, yes. BW's coded surrender. I know it well.

At least your imagination is vivid.
Of course. I reply to posts by people on alt.g-w who can only be
figments of it. No real person could post the nonsense you and
others serve up.
Things you don't understand are not necessarily "nonsense".

Where have I said what I didn't understand was automatically nonsense.
Shall I repeat myself?
When you can explain exactly why you think they're "nonsense",
someone might take you seriously.
In general that is just not the case. You have gone to great lengths
to say that the hypothesis of AGW is nonsense, yet even a complete
nonce like Dubyah doesn't take that proposition seriously any more.
What's his opinion got to do with science? Oh, yeah, I remember. When
you're lost, you try to change the subject.
Now THAT's really pathetic.

I'm glad you recognize that. Now I'll try to stop doing it.

I corrected your typo. Remember to say thank you when you reply.

Look up a couple of lines to note the subject of this particular
paragraph.

I'll spell it out. Subject of paragraph = what is nonsense. This leads
to: Is AGW nonsense? You think yes. Bush now thinks no. Someone
explained the "nonsense" to him and he took it seriously. No subject
change involved; it answers your point. Your red herring was very
pathetic.

Opinion doesn't count in science, only in politics and religion. Even
(especially?) presidential opinion. But nice try.

You should give up trying to change the subject. Suggesting I'm
confused is wishful thinking on your part but there are people reading
this who might get that way.

On second thoughts, naw. It's just thee and me reading it now.

Or were you referring to my mentioning the possibility that someone might
take you seriously? So far, that's pretty unlikely. Until then, you'll just have to pretend others "surrender" to
your superior faith.

"Bill Ward" wrote
Well, I'm done with you and your pathetic word games. If you want
to claim I "surrendered", then you're clearly using the Black Knight
strategy. You can shout whatever you want as I move on. Bye.

It's called - Cut and run.... The final KKKonservative strategy when
losing a battle.

NOAA: 2nd Warmest March on Record for Globe
Global Land Surface Temperature Warmest on Record


The average global temperature (land and ocean surface combined) for last
month was the 2nd warmest on record for March, while the average temperature
for the contiguous U.S. was near average (ranking the 63rd warmest),
according to an analysis by NOAA's National Climatic Data Center in
Asheville, N.C.



Global Highlights

The global surface (land and ocean surface) temperature was the 2nd warmest
on record for March in the 129-year record, 1.28° F (0.71° C) above the 20th
century mean of 54.9° F (12.7° C). The warmest March on record (+1.33°
F/0.74° C) occurred in 2002.

The global land surface temperature was the warmest on record for March,
3.3° F (1.8° C) above the 20th century mean of 40.8° F (5.0° C).
Temperatures more than 8° F above average covered much of the Asian
continent. Two months after the greatest January snow cover extent on record
on the Eurasian continent, the unusually warm temperatures led to rapid snow
melt, and March snow cover extent on the Eurasian continent was the lowest
on record.

Although the ocean surface average was only the 13th warmest on record, as
the cooling influence of La Niña in the tropical Pacific continued, much
warmer than average conditions across large parts of Eurasia helped push the
global average to a near record high for March.

Northern Hemisphere snow cover extent was the fourth lowest on record for
March, remaining consistent with boreal spring conditions of the past two
decades, in which warming temperatures have contributed to anomalously low
snow cover extent.

Some weakening of La Niña, the cold phase of the El Niño-Southern
Oscillation, occurred in March, but moderate La Niña conditions remained
across the tropical Pacific Ocean.

On Apr 17, 10:06 pm, Bill Ward wrote:
On Thu, 17 Apr 2008 11:51:05 -0700, John M. wrote:
On Apr 17, 5:46 pm, Bill Ward wrote:
On Thu, 17 Apr 2008 04:05:28 -0700, John M. wrote:
On Apr 17, 1:53 am, Bill Ward wrote:
On Wed, 16 Apr 2008 14:19:15 -0700, John M. wrote:
On Apr 16, 10:00 pm, Bill Ward
wrote:
On Wed, 16 Apr 2008 10:54:34 -0700, John M. wrote:

wrote:
On Sat, 12 Apr 2008 00:32:46 -0700, John M. wrote:
On Apr 12, 1:49 am, Bill Ward
wrote:

big snip

Is the qualifier "fitting" as in "fitting error" over your head
also?

Nope. Though I note my sarcasm is over yours, it seems.

No riposte. Are you running out of steam. Or perhaps you'd like me to
snip some of the irrelevant material in this sub-thread ;-)

Yes, or no? Or can you not find my post material because of all the
useless and extraneous stuff that I have steadfastly refused to cut, so as
not to give you an excuse for more of your nonsense about snipping is bad
because bandwidth is cheap?

So I didn't snip and BW didn't answer. He had the perfect excuse - he
couldn't find it because of all the extraneous guff. Now we know why
he objects to snipping.

It's referring to a residual as a fitting error because it is the
difference between the model projection and the actual data. IOW
how well the model "fits" the data, as I explained previously.
That's what I find so humorous - your "rebuttal" actually
confirmed my explanation, but you had no clue. There is no need
for me to rewrite the wiki, as it is correct AFAIC.

That wasn't what you implied though, was it? start quote
Wiki? Whoopteedoo. I'm so impressed. Is that the best google
hit
you
could find?
end quote

You see implications that aren't there.

Bill the denialist at work, as ever.

Oh go on. Deny it ;-)

I Thought he wouldn't.

I'm glad you now seem to comprehend the meaning of this particular
jargon. Another jargon word above that you seem to be mystified by
is systematic which you refer to as "systemic". These errors are
only a problem in repetetive data gathering if observers make
changes to their protocol or if data sets from different observers
are merged. I recommend you read my paper on the subject in "The
Ring" 26(1) pp71 - 78 (2004).

You were wise to shift from chemistry to birds - you wouldn't get far
in experimental science.

Is that a comment made after reading my paper, or instead of? Don't
bother to answer. I'm sure I already know and the question becomes
rhetorical.

Wasn't it nice of me to save you that embarrassment.

Not even a thank you from BW.

snip

No, I'm referring specifically to the measurement error, not the
fitting error. Apparently you didn't read the next paragraph. Pay
attention.
I read all the paragraphs. The difference between us is that I
understand them while it seems you cannot or will not.

If you mean measurement error you also need to specify which kind of
measurement errors. These can not only be systematic ("systemic" is a
different word by-the-way and is not used in this context by
staisticians) or random (as in white noise) but also due to rounding
continuous variables before compounding into ratios or other derived
forms of the variable. But having read my paper you already know this,
right?

You are confusing measurement error with data handling error.

Nope. That's not what I'm talking about. That is yet another form of
error.

Statisticians don't necessarily need to know the difference, but
instrument designers and experimentalists do. Measurement error occurs
between the "true value" and the output of the sensor.

So to return to my point that there are various measurement errors. The
sensor may have been mis-calibrated or have drifted out of calibration -
systematic error occurs. An earth tremor or large lorry passing by the lab
might upset movement sensitive components - a random error. The sensor
might give output to three significant figures - a possible rounding error
between 0.5% and ca. 0.05%. All three can be classed as measurement
errors, yet each needs to be addressed differently by an investigator
trying to get a useable value for a variable.

You could argue
over whether a microprocessor program is part of the sensor, but after
the value is available to the user, data handling errors take over, such
as trying to "correct" corrupt data, which was my original point.

Your original point is still here in the thread and you should have re-
read it before posting. start quote Only if you can prove the assumption
that all errors are symmetrically distributed. Otherwise it's a fantasy.
Or a hoax.
end quote

No mention of what you meant by "errors", of which one now identifies four
distinct types, three of which class as measurement error (collectively
resulting in 'residuals') and one due to (perhaps inept or deceitful) data
handling. The importance of being precise in choice of jargon impresses
itself on me at this point. I trust it does likewise to you.

Absence of a response presumably means agreement. We finally got
there.

snip

Things you don't understand are not necessarily "nonsense".

Where have I said what I didn't understand was automatically
nonsense.

Shall I repeat myself?

I suppose not.

snip

I corrected your typo. Remember to say thank you when you reply.

It looked rather that you showed your desperation by editing my post.

Nope. I edited BW's quoted words in my response, AND jokingly
indicated, quite clearly, that I had done so. I guess this proves BW
lacks any sense of humour whatsoever.

That's not acceptable. If you want to be snide, add text of your own,
don't change mine.

If I wanted to be snide I'd forge a post, complete with BW's sig and
addy, and send it from a cyber cafe through an anonymous remailer.

snip

Well, I'm done with you and your pathetic word games. If you want
to claim I "surrendered", then you're clearly using the Black Knight
strategy. You can shout whatever you want as I move on. Bye.

Thank goodness for that; I can go ahead and trim the redundant
material, without let or hindrance from BW. He can get back to
watching the MPFC film I first saw over thirty years ago, paying
particular attention to the siege of Eilean Donan castle and the words
of the French nobleman to the English "kerniggets".

On Apr 18, 9:47 am, "V-for-Vendicar"
wrote:
"Bill Ward" wrote

Well, I'm done with you and your pathetic word games. If you want
to claim I "surrendered", then you're clearly using the Black Knight
strategy. You can shout whatever you want as I move on. Bye.

It's called - Cut and run.... The final KKKonservative strategy when
losing a battle.

Actually, it seems as if he may have agreed on one thing. See my reply
to his post.

NOAA: 2nd Warmest March on Record for Globe
Global Land Surface Temperature Warmest on Record

The average global temperature (land and ocean surface combined) for last
month was the 2nd warmest on record for March, while the average temperature
for the contiguous U.S. was near average (ranking the 63rd warmest),
according to an analysis by NOAA's National Climatic Data Center in
Asheville, N.C.

Global Highlights

The global surface (land and ocean surface) temperature was the 2nd warmest
on record for March in the 129-year record, 1.28� F (0.71� C) above the 20th
century mean of 54.9� F (12.7� C). The warmest March on record (+1.33�
F/0.74� C) occurred in 2002.

The global land surface temperature was the warmest on record for March,
3.3� F (1.8� C) above the 20th century mean of 40.8� F (5.0� C).
Temperatures more than 8� F above average covered much of the Asian
continent. Two months after the greatest January snow cover extent on record
on the Eurasian continent, the unusually warm temperatures led to rapid snow
melt, and March snow cover extent on the Eurasian continent was the lowest
on record.

Although the ocean surface average was only the 13th warmest on record, as
the cooling influence of La Ni�a in the tropical Pacific continued, much
warmer than average conditions across large parts of Eurasia helped push the
global average to a near record high for March.

Northern Hemisphere snow cover extent was the fourth lowest on record for
March, remaining consistent with boreal spring conditions of the past two
decades, in which warming temperatures have contributed to anomalously low
snow cover extent.

Some weakening of La Ni�a, the cold phase of the El Ni�o-Southern
Oscillation, occurred in March, but moderate La Ni�a conditions remained
across the tropical Pacific Ocean.

On Apr 14, 6:17*pm, Roger Coppock wrote:
On Apr 14, 5:23*pm, "
wrote:





On Apr 13, 1:18*pm, "V-for-Vendicar"

wrote:
wrote

*According to the more reliable UAH, *it was the second coldest March
since 2000

2001. *You can't even read your own reference.

MMMMMMMMOOOOOOOOOORRRRRRRRRRRROOOOOOOONNNNNNNN

* As usual, Vendicar spews his lying insults. *Lets see,
*March 2008
shows a temperature anomaly of + 0.094.

March 2007 *+ 0.403
March 2006 *+0.325
March 2005 *+0.351
March 2004 *+0.202
March 2003 +0.220
March 2002 +0.376
March 2001 +0.160
March 2000 + 0.059.

*March 2000 was the only colder month since 2000, that Makes March
2008 the second coldest month since 2000, as I stated before. *March
2008 was the COLDEST March in the 21st century- A. McIntire

- A. McIntire

wrote
. March 2008 was the COLDEST March in the 21st century- A. McIntire

Claims a well known KKKonservative liar.

Now what does the science say?

March the warmest on record over world land surfaces By RANDOLPH E. SCHMID,
AP
Science Writer - April 17, 2998



WASHINGTON - Planet Earth continues to run a fever. Last month was the
warmest
March on record over land surfaces of the world and the second warmest
overall
worldwide. For the United States, however, it was just an average March, the
National Oceanic and Atmospheric Administration reported Thursday.

NOAA's National Climatic Data Center said high temperatures over much of
Asia
pulled the worldwide land temperature up to an average of 40.8 degrees
Fahrenheit (4.9 degrees Celsius), 3.2 degrees (1.8 C) warmer than the
average in
the 20th century.

While Asia had its greatest January snow cover this year, warm March
readings
caused a rapid melt and March snow cover on the continent was a record low.
Global ocean temperatures were the 13th warmest on record, with a weakening
of
the La Nina conditions that cool the tropical Pacific Ocean.

Overall land and sea surface temperatures for the world were second highest
in
129 years of record keeping, trailing only 2002, the agency said.

Warming conditions in recent decades have continued to raise concern about
global climate change, which many weather and climate experts believe is
related
to gases released into the atmosphere by industrial and transportation
processes.

The climate center said that for the 48 contiguous United States it was
about
average, ranking as the 63rd warmest March in 113 years of record keeping.
The average temperature for the U.S. in March was 42 degrees, 0.4 degrees
below
the 20th century mean.

The agency said only Rhode Island, New Mexico and Arizona were warmer than
average, while near-average temperatures occurred in 39 other states. The
monthly temperature for Alaska was the 17th warmest on record.

The snow pack declined in many parts of the West in March, but the Western
snow
pack remains the best in more than a decade thanks to heavy snowfall
December
through February.

For the month, nine states from Oklahoma to Vermont were much wetter than
average, with Missouri experiencing its second wettest March on record.
Moderate to extreme drought remains in much of the Southeast despite
rainfall in
the middle of the month.

On Apr 19, 1:51*pm, "V-for-Vendicar"
wrote:
wrote

. March 2008 was the COLDEST March in the 21st century- A. McIntire



* Now what does the science say?

March the warmest on record over world land surfaces By RANDOLPH E. SCHMID,
AP
Science Writer - April 17, 2998

(cut) Gee, I give a link to UAH actual measurements, you give a
link
to an AP story, and with no documentation whatsoever, have the
chutzpah to call me a liar?-


YOU alleged the earth is warming up at a rate of 10C
per century, then posted

"I have made no such statements.", despite your
Friday, May 11, 2007 post.

http://groups.google.com/group/alt.g...4768b8c?dmode=
=3Dsource

"The fact is, 27'C is a much more reasonable estimate of the future
climate
that some estimates show as being 10'C hotter than today. The global
average then rises from 15'C to 25'C."

- You're a habitual liar- A. McIntire

wrote
(cut) Gee, I give a link to UAH actual measurements, you give a
link to an AP story, and with no documentation whatsoever, have the
chutzpah to call me a liar?

Yup.

From the NOAA.........

http://www.noaanews.noaa.gov/stories...archstats.html

The average global land temperature last month was the warmest on record and
ocean surface temperatures were the 13th warmest. Combining the land and the
ocean temperatures, the overall global temperature ranked the second warmest
for the month of March. Global temperature averages have been recorded since
1880.